# W5 LB scorecard & analysis update 0611

Please upvote if you think this is usefull to follow, then I know if it's good to continue the updates and not creating lots of spam :) And for you who click the downvote, this is not a state-of-the-art scorecard, please contribute with a new scorecard, you probably do better than me at this, I just making a good try :)
An idea to the scorecard is also to get more use of the analysis and see some patterns that helps to create better models and predictions to those in need e.g. identify models there are better in short, medium and long term, use them thereafter and combine them.
Explanation to the columns:
Score diff - is the % difference between 2 LB scores(1d = 1 day difference)
Dist. to the top - distance to the leader.
Models - which technique(LGB, math, Fastai etc) that are used in the models, in top 20, can be interesting to have and follow. Because a team has two submission, I just add what I see, and complements ahead to the team's total.
Diff from last day - the difference between the distance to the leader, from yesterday, approach the leader or lose momentum.
KPI "1d(day) best mover…" - Total move(score difference) the group did against the leader and the individual contribution. Track the individual movement within the group against the leader, see the performance in that timeline regardless what speed has as a whole.
Prediction Top20, 1, 3 & 5 day ahead predictions with calc -
TodayScore+(((TodayScore-YesterdayScore)+((TodayScore-prev5dscore)/5))/2)PredDayAhead
One can calculate in many different ways to see that comparison, this was a quick way to do it.
Also check notebooks below for more analysis.
[https://www.kaggle.com/gaborfodor/w5-top-submissions](https://www.kaggle.com/gaborfodor/w5-top-submissions)
[https://www.kaggle.com/david1013/covid-19-week-5-daily-predictions-top-teams/](https://www.kaggle.com/david1013/covid-19-week-5-daily-predictions-top-teams/)